|
|
Image processing of data from the ultrasound system GE VingMed System Five
Pokorný, Pavel ; Mézl, Martin (referee) ; Harabiš, Vratislav (advisor)
The master thesis is focused on the principle of ultrasonographs and their modes, and ways of denoising data obtained by ultrasonographs. This project will also concentrate on removing the speckle noise, because the speckle noise has the largest share of the noise in the measured data in ultrasonographs. The other main objective was to describe advanced methods of filtration, especially the modifications of the median filter, such as the modified hybrid median filter and modification of the anisotropic diffusion, namely generalizing Perona-Malik anisotropic diffusion using restricted dissimilarity functions. These two filters were tested on images with artificial noise and on data captured using the ultrasound system GE VingMed System FiVe. Also, the program for filtering and display filtered ultrasound data captured by GE VingMed System FiVe is described.
|
|
|
Registration of Ultrasound Image sequences
Kubica, Roman ; Mézl, Martin (referee) ; Jiřík, Radovan (advisor)
The result of this thesis, focused on medical image registration, is an automatic image registration algorithm. It is constructed to be used on real ultrasonography images, created by perfusion imaging. In its introductory part, the thesis deals with registrations methods, next it describes types of optimization principles and single criteria functions served to determine correct image transformation. Based on the theoretical part, there are realized three optimization algorithms using three criterial functions, which served to registration of provided ultrasonography sequences. These algorithms are tested and results are passed on analysis, on its ground are judged its advantages and disadvantages.
|
|
|
Speckle noise suppression methods in ultrasound images
Teplý, Lukáš ; Harabiš, Vratislav (referee) ; Mézl, Martin (advisor)
Ultrasound investigation is one of meaningful imaging at present. Advantages of ultrasound are, that it hasn´t side effects as a rtg radiation and it is noninvasive. Ultrasound diagnostic is exploited in all branch of medicine (urology, cardiology, orthopeadist, gynecology etc.) to display organs, tissues and cavities of the human body. We use display in 2D, 3D and most modern display in 4D. We can encounter with many kinds of artifact. Artifacts are described more closely at 3rd chapter. Speckle noise deteriorates informative yiled of ultrasound picture. We try to remove speckle noise by simpler methods or more complex methods of filtration. These methods are described at 5th chapter. Programme for speckle filtering from pictures is part of this master´s thesis.
|
|
|
Speckle noise suppression methods in ultrasound images
Tvarůžek, Marek ; Harabiš, Vratislav (referee) ; Mézl, Martin (advisor)
This diploma thesis deals with the methods of despeckling in ultrasound images. Ultrasound imaging and related artifacts are described in more details. Ultrasound imaging has its pros and cons, where speckle noise is a disadvantage to be solved. Models of origin of this specific noise are referred too. Practical part of this thesis aims on filtering speckled images by basic and advanced filtering methods as are linear filtering, median filtering, application of Frost filter, QGDCT, geometric filtering, anisotropic diffusion filtering and filtering based on wavelet transformation. Results are compared on the basis of objective criteria.
|
|
|
Affine registration of native and contrast-enhanced CT brain images
Chmelík, Jiří ; Mézl, Martin (referee) ; Walek, Petr (advisor)
This thesis is dealing with problem of brain images registration aquired by computed tomography. At the beginning is explanation of image geometrical transformation methods, notably affine transformation. Following part of text the is dealing with interpolation methods issues, calculation of similarity criterion and subsequent optimalization. All issues are handled especially for three-dimensional data. Second part of this work is practical sample of MatLab® program enviroment for registration of acquired frames by affine tranformation. In this program is algorithm for removement of stair-step artefact, under head pillow and patient’s desk, too. As an optimalization algorithm is used control random search (CRS) methode. Due to medical images type, which are distributed in DICOM format, is included process for their load and save at this work.
|
|
|
Phantom model for perfusion imaging
Borovičková, Michaela ; Harabiš, Vratislav (referee) ; Mézl, Martin (advisor)
This work focuses on issues relating to the perfusion analysis. The aim of this work is to perform experimental measurements of the phantom and then evaluate the perfusion curves. This curves are used to himation of perfusion hemodynamic parameters, which indicates important informatik about monitoring area. All processes associated with the designation and evaluation are performed in a program named Matlab. The output of work is a system that provides the reader into the problem of perfusion analysis and allows him to understand and know what is the meaning od analysis, what demands are placed on the evaluation and what is the result of this perfusion analysis.
|
|
|
Evolutionary Algorithms
Szöllösi, Tomáš ; Mézl, Martin (referee) ; Kozumplík, Jiří (advisor)
The task of this thesis was focused on comparison selected evolutionary algorithms for their success and computing needs. The paper discussed the basic principles and concepts of evolutionary algorithms used for optimization problems. Author programmed selected evolutionary algorithms and subsequently tasted on various test functions with exactly the given input conditions. Finally the algorithms were compared and evaluated the results obtained for different settings.
|
|
|
Optimization method based on TRUST for image registration
Pernicová, Lenka ; Mézl, Martin (referee) ; Harabiš, Vratislav (advisor)
The aim of the thesis is optimization for a medical images registration. The basis is to acquaint with the images registration and to peruse component global optimization methods, especially an optimization method TRUST. After theoretic knowledge it is possible to proceed to a suggestion of an optimization method based on the TRUST method and to realize in the program setting MATLAB. Created algorithms has been tested on test data and compared with other optimization methods as Simulated annealing.
|
|
|
Optimization based on genetic algorithms for image registration
Horáková, Pavla ; Mézl, Martin (referee) ; Harabiš, Vratislav (advisor)
Diploma thesis is focused on global optimization methods and their utilization for medical image registration. The main aim is creation of the genetic algorithm and test its functionality on synthetic data. Besides test functions and test figures algorithm was subjected to real medical images. For this purpose was created graphical user interface with choise of parameters according to actual requirement. After adding an iterative gradient method it became of hybrid genetic algorithm.
|
|
|
Advanced Data Mining in Cardiology
Mézl, Martin ; Provazník, Ivo (referee) ; Sekora, Jiří (advisor)
The aim of this master´s thesis is to analyse and search unusual dependencies in database of patients from Internal Cardiology Clinic Faculty Hospital Brno. The part of the work is theoretical overview of common data mining methods used in medicine, especially decision trees, naive Bayesian classifier, artificial neural networks and association rules. Looking for unusual dependencies between atributes is realized by association rules and naive Bayesian classifier. The output of this work is a complex system for Knowledge discovery in databases process for any data set. This work was realized with collaboration of Internal Cardiology Clinic Faculty Hospital Brno. All programs were made in Matlab 7.0.1.
|
guest ::
